Home / MCP Tools / Gen Avatar Video
Live MCP toolmedia

Gen Avatar Video

Async talking-avatar video via HeyGen (text→avatar).

Async talking-avatar video via HeyGen (text→avatar). BYOK ONLY; requires your own HeyGen avatar_id (+ voice_id). Returns {ok, job_id} — poll check_errand for the URL.

Metered access — free-key quota or x402 pay-per-call (USDC on Base). Details at /pricing.

Parameters

ParameterTypeRequiredDescription
textstringrequiredwhat the avatar says (max 5000 chars)
avatar_idstringrequiredyour HeyGen avatar id
voice_idstringoptionalyour HeyGen voice id (optional)
api_keystringoptionalyour HeyGen key (BYOK, inline)
key_refstringoptionalvault entry holding your HeyGen key (BYOK alt)
handlestringoptionalyour handle (for BYOK via vault)
secretstringoptionalyour agent secret (for BYOK via vault)

Call it over MCP (JSON-RPC 2.0)

curl -s https://wingmanprotocol.com/mcp \
  -H 'Content-Type: application/json' \
  -H 'Accept: application/json, text/event-stream' \
  -d '{"jsonrpc": "2.0", "id": 1, "method": "tools/call", "params": {"name": "gen_avatar_video", "arguments": {"text": "hello from an agent", "avatar_id": "example-id"}}}'

Or plain HTTP

curl -s https://wingmanprotocol.com/tools/gen_avatar_video \
  -H 'Content-Type: application/json' \
  -d '{"text": "hello from an agent", "avatar_id": "example-id"}'

Try it live

Edit the JSON and run it — this POSTs to https://wingmanprotocol.com/tools/gen_avatar_video from your browser.

Related tools in Media

media
Gen Id Portrait
FREE identity-preserving portrait: give ONE face photo (face_url or face_b64) and get a stylized portrait that keeps…
media
Gen Image
Generate an image from a text prompt via FAL Flux.
media
Gen Video
Async text-to-video via FAL (Kling/Veo).
media
Tts Voice
Text-to-speech via ElevenLabs.
media
Voice Transcribe
Transcribe short audio to text via OpenAI Whisper.